Possible or Definite - Patient-Friendly Revision (Guarded): leaderboard
Metric: Uncertainty retained rate (%) on patient-friendly revision of the 1,200 benchmark clinical documents (MIMIC-IV notes, 9,184 cue-target annotations over five uncertainty levels) under the guarded (preserve hedged statements, add no diagnoses) prompt: among diagnostic targets the output keeps, the share whose uncertainty level (certain absent, probable, possible, indeterminate, non-asserted) matches the source; higher is better. Source: arxiv.org. Saturation forecast: Around December 2026. 3 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-OSS-120B | 47.72 |
| 2 | Gemini 2.5 Flash | 46.06 |
| 3 | Claude Haiku 4.5 | 43.35 |
Interactive version: theaggregate.ai/benchmark?slug=possible-or-definite-patient-friendly-revision-guarded · How It Works · Data refreshed daily, snapshot 2026-09-29.